Interaction between multiple agents requires some form of coordination and a level of mutual awareness. When computers and robots interact with people, they need to recognize human plans and react appropriately. Plan and goal recognition techniques have focused on identifying an agent's task given a sufficiently long action sequence. However, by the time the plan and/or goal are recognized, it may be too late for computing an interactive response. We propose an integration of planning with probabilistic recognition where each method uses intermediate results from the other as a guiding heuristic for recognition of the plan/goal in-progress as well as the interactive response. We show that, like the used recognition method, these interaction problems can be compiled into classical planning problems and solved using off-the-shelf methods. In addition to the methodology, this paper introduces problem categories for different forms of interaction, an evaluation metric for the benefits from the interaction, and extensions to the recognition algorithm that make its intermediate results more practical while the plan is in progress.

Learning fast and efficiently using minimal data has been consistently a challenge in machine learning. In my thesis, I explore this problem for knowledge transfer for multi-agent multi-task learning in a life-long learning paradigm. My goal is to demonstrate that by sharing knowledge between agents and similar tasks, efficient algorithms can be designed that can increase the speed of learning as well as improve performance. Moreover, this would allow for handling hard tasks through collective learning of multiple agents that share knowledge. As an initial step, I study the problem of incorporating task descriptors into lifelong learning of related tasks to perform zero-shot knowledge transfer. Zero-shot learning is highly desirable because it leads to considerable speedup in handling similar sequential tasks. Then I focus on a multi-agent learning setting, where related tasks are learned collectively and/or address privacy concerns.

We consider Max-min Share (MmS) fair allocations of indivisible chores (items with negative utilities). We show that allocation of chores and classical allocation of goods (items with positive utilities) have some fundamental connections but also differences which prevent a straightforward application of algorithms for goods in the chores setting and vice-versa. We prove that an MmS allocation does not need to exist for chores and computing an MmS allocation - if it exists - is strongly NP-hard. In view of these non-existence and complexity results, we present a polynomial-time 2-approximation algorithm for MmS fairness for chores. We then introduce a new fairness concept called optimal MmS that represents the best possible allocation in terms of MmS that is guaranteed to exist. We use connections to parallel machine scheduling to give (1) a polynomial-time approximation scheme for computing an optimal MmS allocation when the number of agents is fixed and (2) an effective and efficient heuristic with an ex-post worst-case analysis.

In the late 19th century, Lars Edvard Phragmén proposed a load-balancing approach for selecting committees based on approval ballots. We consider three committee voting rules resulting from this approach: two optimization variants one minimizing the maximal load and one minimizing the variance of loads —and a sequential variant. We study Phragmén's methods from an axiomatic point of view, focussing on justified representation and related properties that have recently been introduced by Aziz et al. (2015a) and Sánchez-Fernández et al. (2017). We show that the sequential variant satisfies proportional justified representation, making it the first known polynomial-time computable method with this property. Moreover, we show that the optimization variants satisfy perfect representation. We also analyze the com- putational complexity of Phragmén's methods and provide mixed-integer programming based algorithms for computing them.

It's been a long time worry that when AI gains a certain level of autonomy it will see no use for humans or even perceive them as a threat. A new study by Google's DeepMind lab may or may not ease those fears. There are two unmistakable sides to the debate concerning the future of artificial intelligence. The researchers at DeepMind have been working with two games to test whether neural networks are more likely to understand motivations to compete or cooperate. They hope that this research could lead to AI being better at working with other AI in situations that contain imperfect information.

When our robot overlords arrive, will they decide to kill us or cooperate with us? New research from DeepMind, Alphabet Inc.'s London-based artificial intelligence unit, could ultimately shed light on this fundamental question. They have been investigating the conditions in which reward-optimizing beings, whether human or robot, would choose to cooperate, rather than compete. The answer could have implications for how computer intelligence may eventually be deployed to manage complex systems such as an economy, city traffic flows, or environmental policy. Joel Leibo, the lead author of a paper DeepMind published online Thursday, said in an e-mail that his team's research indicates that whether agents learn to cooperate or compete depends strongly on the environment in which they operate.

On the Web, there is always a need to aggregate opinions from the crowd (as in posts, social networks, forums, etc.). Different mechanisms have been implemented to capture these opinions such as "Like" in Facebook, "Favorite" in Twitter, thumbs-up/down, flagging, and so on. However, in more contested domains (e.g. Wikipedia, political discussion, and climate change discussion) these mechanisms are not sufficient since they only deal with each issue independently without considering the relationships between different claims. We can view a set of conflicting arguments as a graph in which the nodes represent arguments and the arcs between these nodes represent the defeat relation. A group of people can then collectively evaluate such graphs. To do this, the group must use a rule to aggregate their individual opinions about the entire argument graph. Here, we present the first experimental evaluation of different principles commonly employed by aggregation rules presented in the literature. We use randomized controlled experiments to investigate which principles people consider better at aggregating opinions under different conditions. Our analysis reveals a number of factors, not captured by traditional formal models, that play an important role in determining the efficacy of aggregation. These results help bring formal models of argumentation closer to real-world application.

Understanding how logical agents cooperate or fight, especially in the face of resource scarcity, is a fundamental problem for social scientists. But soon, this problem will also be at the heart of how we understand, control, and cooperate with artificially intelligent agents, and how they work among themselves. Researchers inside of Google's AI DeepMind project wanted to know whether distinct artificial intelligence agents worked together or competed when faced with a problem. Doing this experiment would help scientists understand how our future networks of smart systems may work together. The researchers pitted two AIs against each other in a couple of video games.

Google's artificial intelligence subsidiary DeepMind is pitting AI agents against one another to test how they interact with each other and how they would react in various "social dilemmas". In a new study, researchers said they used two video games – Wolfpack and Gathering – to examine how AI agents change the way they behave based on the environment and situation they are in using social sciences and game theory principles. "The question of how and under what circumstances selfish agents cooperate is one of the fundamental questions in the social sciences," DeepMind researchers wrote in a blog post. "One of the simplest and most elegant models to describe this phenomenon is the well-known game of Prisoner's Dilemma from game theory." This well-known principle is based on the scenario where two arrested suspects jointly accused of a crime are questioned separately.

Bostjan Kaluza, PhD, is a researcher in artificial intelligence and machine learning. Bostjan is the chief data scientist at Evolven, a leading IT operations analytics company, focusing on configuration and change management. He works with machine learning, predictive analytics, pattern mining, and anomaly detection to turn data into understandable relevant information and actionable insight. Prior to Evolven, Bostjan served as a senior researcher in the department of intelligent systems at the Jozef Stefan Institute, a leading Slovenian scientific research institution, and led research projects involving pattern and anomaly detection, ubiquitous computing, and multi-agent systems. Bostjan was also a visiting researcher at the University of Southern California, where he studied suspicious and anomalous agent behavior in the context of security applications.